Skip to main content
Browse Subject Areas

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Disaggregating Census Data for Population Mapping Using Random Forests with Remotely-Sensed and Ancillary Data

Fig 7

Visual comparisons of GRUMP, AfriPop and the RF-based population map from this study.

Though this region northwest of Nairobi, Kenya is not a highly populated region this figure shows the results of the more detailed RF weighting layer versus the use of just urban areas (GRUMP) and land cover plus urban areas (AfriPop). The distinct edges in estimated people per pixel between census units are almost eliminated by the RF approach and it achieves greater consistency in predicted population density after census count redistribution.

Fig 7